Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zeng, Xiong, Bako, Laurent, Ozay, Necmiye
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909442084175872
author Zeng, Xiong
Bako, Laurent
Ozay, Necmiye
author_facet Zeng, Xiong
Bako, Laurent
Ozay, Necmiye
contents In this paper, we study the noise sensitivity of the semidefinite program (SDP) proposed for direct data-driven infinite-horizon linear quadratic regulator (LQR) problem for discrete-time linear time-invariant systems. While this SDP is shown to find the true LQR controller in the noise-free setting, we show that it leads to a trivial solution with zero gain matrices when data is corrupted by noise, even when the noise is arbitrarily small. We then study a variant of the SDP that includes a robustness promoting regularization term and prove that regularization does not fully eliminate the sensitivity issue. In particular, the solution of the regularized SDP converges in probability also to a trivial solution.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19705
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR
Zeng, Xiong
Bako, Laurent
Ozay, Necmiye
Optimization and Control
Systems and Control
In this paper, we study the noise sensitivity of the semidefinite program (SDP) proposed for direct data-driven infinite-horizon linear quadratic regulator (LQR) problem for discrete-time linear time-invariant systems. While this SDP is shown to find the true LQR controller in the noise-free setting, we show that it leads to a trivial solution with zero gain matrices when data is corrupted by noise, even when the noise is arbitrarily small. We then study a variant of the SDP that includes a robustness promoting regularization term and prove that regularization does not fully eliminate the sensitivity issue. In particular, the solution of the regularized SDP converges in probability also to a trivial solution.
title Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2412.19705